毕业设计---基于BP人工神经网络对汽轮机组凝汽系统做出故障诊断

1、 1 摘要摘要 凝汽器运行的热力性能对汽轮机机组运行的安全性与经济性有很重要的影响，研 究凝汽器故障诊断方法，实施故障诊断技术对提高机组经济运行水平有着重要的理论意义 和工程实用价值。 本文论述了火电厂凝汽设备的运行特性，分析了凝汽系统的常见故障，重点分析了凝 汽器真空恶化的原因及征兆;全面阐述了 BP 神经网络的基本理论和系统结构，设计了神经 网络应用于故障诊断领域。以 BP 神经网络为基础建立凝汽器故障诊断专家系统，对网络 进行训练，然后利用所学成的网络，对凝汽器故障数据进行处理，得到了凝汽器具体的故 障情况。 本文利用 MATLAB6.5 作为工具，利用神经网络的学习规则，采用自适应学习

2、率 BP 算 法完成故障知识库的组建;使用 MATLAB6.5 基于 BP 人工神经网络对汽轮机组凝汽系统做出 故障诊断。 关键词:凝汽器;故障诊断;神经网络;专家系统 BSTRACT The thermodynamic characteristic of condensing system has a heavy impaction on the security and economy of a running turbine. It is important that establishing the monitoring and optimization model for fault

3、 diagnosis and improving the operation level. In this paper, condensing system is performance is discussed and condensing system s common faults are analyzed and the cause and signs of condenser is vacuum falling are emphasized . The basic theory and system structure of Artificial Neural Network and

4、 Expert System are introduced in this paper. It designs a new method which combines the Experts System with the Artificial Neural Network to make application for fault diagnosis field better. Combined with each situation in detail, condenser diagnosis Expert System based on BP Neural Network is constructed. Trains Network, and then deals with diagnosis datum through making use of the learned Network. So it obtains diagnosis situation in detail. With MATLAB, making use of the Neural Network le